AI Automation Engineer for UAT Test Management & Defect Reporting

Project Overview We’re looking for an AI Automation Engineer to build an AI-assisted UAT test management and defect reporting workflow. The goal is to reduce manual QA reporting effort, improve test traceability, and give project managers and QA teams better visibility into testing progress. The solution should integrate with Azure DevOps and use n8n to automate workflows, with an LLM such as OpenAI or Claude for test case generation, defect summarization, and reporting. We’re looking for someone who understands both QA processes and AI workflow automation, not just someone who can connect APIs. Scope of Work 1. AI-Assisted Test Case Generation - Generate structured UAT test cases from user stories and business requirements. - Include positive, negative, and edge-case scenarios. - Organize test cases by requirement or user story. - Produce clear steps and expected results for QA review. 2. Azure DevOps Integration - Connect with Azure DevOps using its API. - Retrieve relevant work items, test cases, and execution results where supported by the available project setup. - Maintain traceability between requirements, test execution, and defects. - Handle API errors and missing or incomplete data. 3. Automated Defect Reporting - Process failed test execution results. - Generate structured defect drafts containing: - Clear defect title and summary - Reproduction steps - Expected and actual results - Suggested severity or priority - Links to related requirements and evidence - Include evidence references when available through the source system. - Allow QA review before defects are finalized or submitted. 4. UAT Status Reporting - Generate daily summaries covering: - Total, passed, failed, and blocked tests - Execution progress - Open defects and critical issues - Outstanding testing activities - Overall UAT readiness indicators - Deliver reports through email or Slack, depending on the agreed scope. 5. n8n Workflow Automation - Build reusable n8n workflows with conditional logic. - Add basic error handling, logging, and retry mechanisms. - Keep API credentials secure. - Provide a clear workflow structure that can be maintained and extended. Preferred Technology Stack - n8n - Azure DevOps REST API - OpenAI API or Claude API - REST API integrations - Python, where needed - Slack or email automation - GitHub for source control and handover Deliverables 1. Working n8n workflow for the agreed MVP scope. 2. Azure DevOps integration with the agreed data and operations. 3. AI-generated test case and defect report examples. 4. Automated UAT status report. 5. Basic error handling and testing evidence. 6. Exportable n8n workflow JSON and any supporting source code. 7. Setup instructions and handover documentation. Acceptance Criteria - The workflow can process sample requirements and generate reviewable UAT test cases. - Failed test results produce structured defect drafts with the available evidence and traceability links. - UAT status reports accurately reflect the supplied test execution data. - AI-generated severity suggestions and defect classifications remain subject to human QA approval. - The workflow can be imported and configured using the provided documentation. Ideal Candidate - Experience building n8n automation workflows. - Strong understanding of software QA, UAT, test case design, and defect lifecycle management. - Experience integrating Azure DevOps or similar test management platforms. - Hands-on experience with OpenAI or Claude APIs. - Comfortable with REST APIs, authentication, debugging, and error handling. - Able to deliver maintainable workflows with clear documentation. We plan to start with a clearly defined MVP, with potential for additional workflow enhancements and ongoing collaboration if the initial delivery goes well.